ArgoCD MCP Server is a Model Context Protocol (MCP) server that integrates the ArgoCD GitOps continuous delivery tool with GenAI applications for intelligent Kubernetes deployment management.
From the registry: MCP server for ArgoCD GitOps continuous delivery integration
$ pip install argocd-mcp-serverPlease install the `argocd-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install argocd-mcp-server** — Install via pip Run: `pip install argocd-mcp-server`
- **ArgoCD auth token** — Obtain an ArgoCD auth token from your ArgoCD instance
Canonical MCP server config (stdio transport):
- command: `python`
- args: ["-m","argocd_mcp.server"]
- required environment variables:
- `ARGOCD_SERVER`: ArgoCD server URL (example: `argocd.example.com`)
- `ARGOCD_AUTH_TOKEN`: ArgoCD auth token (example: `<your_auth_token>`)
- optional environment variables:
- `ARGOCD_INSECURE`: Allow insecure TLS (example: `false`)
- `ARGOCD_GRPC_WEB`: Use gRPC-web (example: `true`)
- `ARGOCD_TIMEOUT`: Request timeout (seconds) (example: `30`)
- `ARGOCD_CLIENT_CERT`: Path to client cert PEM (example: `/path/to/cert.pem`)
- `ARGOCD_CLIENT_KEY`: Path to client key PEM (example: `/path/to/key.pem`)
Note: Supports multi-cluster via ARGOCD_<ENV>_SERVER/ARGOCD_<ENV>_TOKEN env pairs.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.ARGOCD_SERVERrequiredThe URL of the ArgoCD server.ARGOCD_AUTH_TOKENrequiredThe authentication token for accessing the ArgoCD server.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.